← Back to context

Comment by Neywiny

5 hours ago

I just started using opus 4.8 and it's still trash at very domain specific stuff and debugging. It went down a rabbit hole trying to coerce the algorithm to work for 1 data point, which dramatically overfit the code. Later it did 11 experiments to try and figure out how to do the math, each one yielding an accuracy no better than a coin flip and each one it asserted beforehand that it had it this time, 100% accuracy.

We've got some time.

That's last gen though. I agree it's mediocre. Try Astra. It's significantly better than Opus and even Fable. I'm not sure about earlier OpenAI models.

I also thought we had time.

  • It seems to depend on the domain, and perhaps the tech stack? I’ve been disappointed by Astra, it’s worse than both Fable and Opus for me.

    • Yeah maybe. I dunno though, I'm using it in obscure SystemVerilog stuff. AI used to absolutely suck at that very recently but now it seems to have no problem.

      I think the key is that you give it all of the info - put all the docs, the LRM, tool manuals, etc. in a directory so it can read it if it wants (it really really wants).